def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. size = self.input_size fname = self.fnames[idx] img_path = os.path.join(self.root, fname) img = Image.open(img_path) att_map, out_catch = self.get_att.get_att(img) if img.mode != 'RGB': img = img.convert('RGB') boxes = torch.zeros(2, 4) img = resize(img, boxes, size, test_flag=True) att_map = resize(att_map, boxes, size, test_flag=True) img = center_crop(img, boxes, (size, size), test_flag=True) att_map = center_crop(att_map, boxes, (size, size), test_flag=True) img = self.transform(img) att_map = self.transform_att(att_map) att_map = torch.floor(100 * att_map) att_map = self.thresh(att_map) #att_map = np.array(att_map, dtype=np.float32) id_ = self.ids[idx] return img, img_path, id_, att_map
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' ####anchor # Load image and boxes. triplet_id = [] triplet_id.append(idx) pos_counter = self.ids.count(self.ids(idx)) pos_id = random.randint(self.ids.count(self.ids(idx)), self.ids.count(self.ids(idx))+pos_counter) triplet_id.append(pos_id) neg = self.ids(idx) neg_id = self.ids[random.randint(0, len(self.ids)-1)] while neg == neg_id: neg_id = self.ids[random.randint(0, len(self.ids)-1)] triplet_id.append(neg_id) tri_img = [] tri_img_path = [] tri_att_map = [] for get_idx in triplet_id: size = self.input_size fname = self.fnames[get_idx] img_path = os.path.join(self.root, fname) tri_img_path.append(img_path) img = Image.open(img_path) att_map, out_catch = self.get_att.get_att(img) if img.mode != 'RGB': img = img.convert('RGB') boxes = torch.zeros(2,4) img = resize(img, boxes, size, test_flag=True) att_map = resize(att_map, boxes, size, test_flag=True) img = center_crop(img, boxes, (size,size), test_flag=True) att_map = center_crop(att_map, boxes, (size,size), test_flag=True) img = self.transform(img) tri_img.append(img) att_map = self.transform_att(att_map) att_map = torch.floor(100*att_map) att_map = self.thresh(att_map) tri_att_map.append(att_map) return tri_img, tri_img_path, triplet_id, tri_att_map
def __getitem__(self, index): img_path = self.fnames[index] bbox = self.bboxs[index] texts = self.texts[index] texts_encoded = self.texts_encoded[index] # loading img img = Image.open(os.path.join(self.path_img_folder, img_path)) if img.mode != 'RGB': img = img.convert('RGB') if self.train: #img, boxes = random_flip(img, bbox) #img, boxes = random_crop(img, bbox) img, boxes = resize(img, bbox, (self.figsize, self.figsize)) else: img, boxes = resize(img, bbox, (self.figsize, self.figsize)) img, boxes = center_crop(img, bbox, (self.figsize, self.figsize)) img = self.transform(img) # scale to -1~1 img = 2 * img - 1 return texts_encoded, img, boxes
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. fname = self.fnames[idx] img = Image.open(os.path.join(self.root, fname)) if img.mode != 'RGB': img = img.convert('RGB') boxes = self.boxes[idx].clone() labels = self.labels[idx] size = self.input_size # Data augmentation. if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, (size, size)) else: img, boxes = resize(img, boxes, size) img, boxes = center_crop(img, boxes, (size, size)) img = self.transform(img) return img, boxes, labels
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. fname = self.fnames[idx] img = Image.open(os.path.join(self.root, fname)) if img.mode != 'RGB': img = img.convert('RGB') boxes = self.boxes[idx].clone() labels = self.labels[idx] size = self.input_size # Data augmentation. if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, (size,size)) else: img, boxes = resize(img, boxes, size) img, boxes = center_crop(img, boxes, (size,size)) img = self.transform(img) return img, boxes, labels
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. size = self.input_size fname = self.fnames[idx] img_path = os.path.join(self.root, fname) img = Image.open(img_path) if img.mode != 'RGB': img = img.convert('RGB') boxes = torch.zeros(2, 4) img = resize(img, boxes, size, test_flag=True) img = center_crop(img, boxes, (size, size), test_flag=True) img = self.transform(img) id_ = self.ids[idx] return img, img_path, id_
def __getitem__(self, index): fname = os.path.join(self.im_pth, self.fnames[index]) img = Image.open(fname) if img.mode!='RGB': img = img.convert('RGB') boxes = self.boxes[index].clone() size = self.size #print(img.size) if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, size) else: img, boxes = center_crop(img, boxes, size) img, boxes = resize(img, boxes, size) if self.transform is not None: img = self.transform(img) dense_map = torch.zeros([1, img.size()[1], img.size()[2]], dtype=torch.float32) #print(dense_map.size()) box_num = 0 for box in boxes: area = (box[2]-box[0])*(box[3]-box[1]) #print(box[0], box[1], box[2], box[3], area) if area<100.: continue box_num += 1 try: dense_map[:, box[1].type(torch.int32):box[3].type(torch.int32), box[0].type(torch.int32):box[2].type(torch.int32)] += 1/area except: print(fname, dense_map.size()) print(box[1].type(torch.int32), box[3].type(torch.int32), box[0].type(torch.int32), box[2].type(torch.int32), area) return img, dense_map, box_num
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. fname = self.fnames[idx] prefix_name = fname[:2] if self.train: image_path = self.root + '/' + prefix_name + '/' + fname else: image_path = self.root + '/' + prefix_name + '/' + fname # img = Image.open(os.path.join(self.root, fname)) img_a = Image.open(image_path + '_a.jpg') img_b = Image.open(image_path + '_b.jpg') img_c = Image.open(image_path + '_c.jpg') img = Image.merge('RGB', (img_a, img_b, img_c)) # if img.mode != 'RGB': # img = img.convert('RGB') boxes = self.boxes[idx].clone() labels = self.labels[idx] size = self.input_size # Data augmentation. if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, (size,size)) else: img, boxes = resize(img, boxes, size) img, boxes = center_crop(img, boxes, (size,size)) img = self.transform(img) # if self.transforms is not None: # # if img is a byte or uint8 array, it will convert from 0-255 to 0-1 # # this converts from (HxWxC) to (CxHxW) as well # img_a, img_b, img_c = image # img_a = self.transforms(img_a) # img_b = self.transforms(img_b) # img_c = self.transforms(img_c) # img = (img_a, img_b, img_c) return img, boxes, labels
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. fname = self.fnames[idx] img = Image.open(os.path.join(self.root, fname)) if img.mode != 'RGB': img = img.convert('RGB') width, height = img.size flabel = fname.replace('images/', 'labels/').replace('.jpg', '.txt').replace( '.png', '.txt').replace('.jpeg', '.txt') box = [] label = [] with open(flabel) as f: lines = f.readlines() for line in lines: ls = line.strip().split() x = float(ls[1]) * width y = float(ls[2]) * height w = float(ls[3]) * width h = float(ls[4]) * height box.append([x - w / 2, y - h / 2, x + w / 2, y + h / 2]) label.append(int(ls[0])) boxes = torch.Tensor(box) labels = torch.LongTensor(label) size = self.input_size # Data augmentation. if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, (size, size)) else: img, boxes = resize(img, boxes, size) img, boxes = center_crop(img, boxes, (size, size)) img = self.transform(img) return img, boxes, labels
def __getitem__(self, idx): '''Load image. Args: idx: (int) image index. Returns: img: (tensor) image tensor. loc_targets: (tensor) location targets. cls_targets: (tensor) class label targets. ''' # Load image and boxes. fname = self.fnames[idx] img_path = os.path.join(self.root, fname) img = Image.open(img_path) if img.mode != 'RGB': img = img.convert('RGB') boxes = self.boxes[idx].clone() labels = self.labels[idx] size = self.input_size src_shape = self.shape_list[idx] att_map = np.zeros([src_shape[0], src_shape[1]]) for att_box in boxes: att_map[int(att_box[0]):int(att_box[2]), int(att_box[1]):int(att_box[3])] = 1 # Data augmentation. if self.train: img, boxes = random_flip(img, boxes) img, boxes = random_crop(img, boxes) img, boxes = resize(img, boxes, (size, size)) else: img, boxes = resize(img, boxes, size) img, boxes = center_crop(img, boxes, (size, size)) att_map = Image.fromarray(att_map) att_map = att_map.resize((size // 2, size // 2), Image.BILINEAR) #img.save('test_in_datagen.jpg') img = self.transform(img) att_map = self.transform(att_map) return img, boxes, labels, att_map, img_path